Vals AI Financial Coaching Bench: leaderboard

Financial Coaching Bench v1 (Vals AI, November2026) tests AI financial coaching on 256 private household scenarios. A simulated client, played by Claude Sonnet4.6, answers from a hidden fact sheet; the coach can ask questions and search the web. This board is mean practitioner-checklist credit in percent, preserving each native model and effort. Length-controlled scores and elicitation diagnostics are separate; higher is better.

Metric: Mean practitioner-checklist credit (%). Source: www.vals.ai. Saturation forecast: Not forecast. 27 models tracked. Updated 14 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Opus 5.5Max76.16#5
2Muse Spark 1.2xHigh75.74#97
3Claude Fable 5.1Max75.71#15
4Qwen 3.8 Max75.58#59
5MiMo-V2.6-Pro75.37#76
6Muse Wonder FullMax74.96#17
7Claude Sonnet 5.5Max74.94#19
8GPT-5.6 SolMax74.89#30
9Kimi K3Max74.53#56
10Grok 4.7xHigh74.07#47
11GLM-5.3Max74.06#68
12Muse WonderMax73.78#28
13Gemini 4 ArgonHigh73.13#12
14DeepSeek V4.1 FlashHigh72.83#62
15Muse Spark 1.3xHigh70.99#43

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=vals-ai-financial-coaching-bench · How It Works · Data refreshed daily, snapshot 2026-11-16.